Ramlinbird

Is there any length limit of the music with this method?

1

Nice to see contrastive learning used in music area, is there any length limit? Is it possible to get meaningful representation (for example, hundreds dimension vector) of song (few minutes...

Hello, @m3hrdadfi , sorry to disturb. I created my own train.csv (4213 records) and dev.csv (527 records) , and run the run_wav2vec_clf.py to train a music genre recognition model, but...

bash: fleetrun: command not found

1

运行PGL/examples/graphsage/下的例子时，`fleetrun`命令找不到  #### 版本、环境信息 - PGL和PaddlePaddle版本号： - paddlepaddle-gpu 2.1.2 - pgl 2.1.5 - 系统环境： - ubuntu - Python 3.6.9

wavlm extract features failed in loop

2

**Describe the bug** Model I am using WavLM, follow the scripts in the wavlm's [README.txt](https://github.com/microsoft/unilm/tree/master/wavlm), (**I modified to gpu device, I have tried cpu mode, the same memory exception.**) ```...

About domain adapation of ernie-3.0

5

Hello, if I have lots of domain unlabel text data, can I continue training domain-adapated ernie-3.0 with the interface of AutoModelForPretraining? Thanks a lot.

About the training of slearner

1

I read the implementation of slearner for estimating causal effects with multiple treatments, and find that it will train multiple models of each treatment-control pair. My question is, can I...

Graph4Rec的CPU分布式训练运行失败

18

您好，我在单机上尝试Graph4Rec说到的单机训练，步骤如下： 1）先修改./toy_data/ip_list.txt文件，填写了ip地址，然后分别启动 ``` python -m pgl.distributed.launch --ip_config ./toy_data/ip_list.txt --conf ./user_configs/metapath2vec.yaml --shard_num 1000 --server_id 0 python -m pgl.distributed.launch --ip_config ./toy_data/ip_list.txt --conf ./user_configs/metapath2vec.yaml --shard_num 1000 --server_id 1 ``` 2）然后执行单机分布训练 ``` CPU_NUM=4 fleetrun...

The function `multilabelConfussionMatrix` in `multilabelMetrics/functions.py` is not right, (may be spelling error) The correct version should be ``` def multilabelConfussionMatrix(y_test, predictions): """ Returns the TP, FP, TN, FN """ TP...